Script-Only Cron Jobs (No LLM)
Script-Only Cron Jobs (No LLM)
Start with meaning, then move to detail.
This lesson explains Script-Only Cron Jobs (No LLM) as part of using Hermes through messaging channels. You will learn what it does, when it matters, and the smallest safe test that proves it works.
If you are new, do not memorize names. Focus on three questions: what problem does this solve, what access does it need, and how can you verify the result?
For practice, inspect the first example, identify its effects, run it on test data, and compare the result with the source claim.
For advanced readers, inspect When to Use It, Create One from Chat, Example transcript, then verify failure modes and version compatibility.
Prepare the channel account and understand allowlists and secret storage.
A clear outcome before you read.
- Understand Script-Only Cron Jobs (No LLM) without assumed prior knowledge.
- Separate the source description from what still needs testing in your environment.
- Read the first command and identify its inputs and outputs before copying it.
Short definitions before the details.
- Automation
- Running work later or repeatedly with explicit success and failure conditions.
Classic watchdog cron jobs that skip the LLM entirely — a script runs on schedule and its stdout gets delivered to your messaging platform. Memory alerts, disk alerts, CI pings, periodic health checks.
What does the source say, and in what order?
- 01When to Use It
Start here to understand the core idea or structure.
- 02Create One from Chat
Read this after the foundation, then connect it to the previous step.
- 03Example transcript
Read this after the foundation, then connect it to the previous step.
- 04What the agent decides for you
Read this after the foundation, then connect it to the previous step.
- 05Managing watchdogs from chat
Read this after the foundation, then connect it to the previous step.
- 06Create One from the CLI
Read this after the foundation, then connect it to the previous step.
- 07How Script Output Maps to Delivery
Read this after the foundation, then connect it to the previous step.
- 08Script Rules
Read this after the foundation, then connect it to the previous step.
- 09Schedule Syntax
Read this after the foundation, then connect it to the previous step.
- 10Delivery Targets
Finish here to verify the result and special cases.
Copy only after you understand the effect.
┌──────────────────┐ ┌──────────────────┐
│ scheduler tick │ every │ run script │
│ (every N minutes)│ ──────▶ │ (bash or python) │
└──────────────────┘ └──────────────────┘
│
│ stdout
▼
┌──────────────────┐
│ delivery router │
│ (telegram/disc…) │
└──────────────────┘From that point on every tick is free: the scheduler runs the script, pipes its stdout to Telegram if non-empty, and never touches a model.
### What the agent decides for you
When you phrase a request like "alert me when X" or "every N minutes check Y and tell me if Z", Hermes' `cronjob` tool description tells it to reach for `no_agent=True` whenever the message content is fully determined by the script. It falls back to the normal LLM-driven path when the request needs reasoning (*"summarize the new issues"*, *"pick the most interesting headlines"*, *"draft a friendly reminder"*).
You don'That's the whole thing. No prompt, no skill, no model.
## How Script Output Maps to Delivery
| Script behavior | Result |
|-----------------|--------|
| Exit 0, non-empty stdout | stdout is delivered verbatim |
| Exit 0, empty stdout | Silent tick — no delivery |
| Exit 0, stdout contains `{"wakeAgent": false}` on the last line | Silent tick (shared gate with LLM jobs) |
| Non-zero exit code | Error alert is delivered (so a broken watchdog doesn't fail silently) |
| Script timeout | Error alert is delivered |
The "silent when empty" behavior is the key to the classic watchdog pattern: the Read the first command and identify its inputs and outputs before copying it.
Match every command to your installed Hermes version, review the files and accounts it can reach, and use non-sensitive data for the first test. If this explanation differs from the source, the official source wins.